New ParatextVPL format

README.md

@@ -140,8 +140,9 @@ SQLite based formats or for importing MyBible.Zone bibles.
 The **ParatextConverter** tool can be used to convert between USFM/USFX/USX formats
 without converting to BibleMultiConverter's internal format first, or to remove
 tagged OT/NT/Deuterocanonical content from such a file. It can also be used to convert
-to **ParatextDump** format (which is a diffable plain text dump of the internal Paratext
-structure and useful for comparing different Paratext formats).
+from/to **ParatextDump** (which is a diffable plain text dump of the internal Paratext
+structure and useful for comparing different Paratext formats) and **ParatextVPL** (which is
+a different diffable format that looks more like VPL, but uses Paratext tags) formats.
 
 The **MyBibleZoneListDownloader** tool (part of SQLite edition) can be used to download
 the list of available MyBible.Zone modules from the module registry (that is also queried

biblemulticonverter/src/main/java/biblemulticonverter/MainModuleRegistry.java

@@ -70,6 +70,7 @@ public Collection<Module<RoundtripFormat>> getRoundtripFormats() {
 		result.add(new Module<RoundtripFormat>("USX", "XML Bible format used by Paratext and the Digital Bible Library (version 2)", USX.HELP_TEXT, USX.class));
 		result.add(new Module<RoundtripFormat>("USX3", "XML Bible format used by Paratext and the Digital Bible Library (version 3)", USX3.HELP_TEXT, USX3.class));
 		result.add(new Module<RoundtripFormat>("ParatextDump", "Dump a Paratext bible to diffable plain text", ParatextDump.HELP_TEXT, ParatextDump.class));
+		result.add(new Module<RoundtripFormat>("ParatextVPL", "VPL inspired format using Paratext tags", ParatextVPL.HELP_TEXT, ParatextVPL.class));
 		result.add(new Module<RoundtripFormat>("RoundtripODT", "ODT export and re-import", RoundtripODT.HELP_TEXT, RoundtripODT.class));
 		result.add(new Module<RoundtripFormat>("BibleWorks", "Plain text import and export format for BibleWorks", BibleWorks.HELP_TEXT, BibleWorks.class));
 		result.add(new Module<RoundtripFormat>("BibleWorksRTF", "RTF import and export format for BibleWorks", BibleWorksRTF.HELP_TEXT, BibleWorksRTF.class));

biblemulticonverter/src/main/java/biblemulticonverter/format/paratext/ParatextBook.java

@@ -10,6 +10,7 @@
 import java.util.Set;
 
 import biblemulticonverter.data.BookID;
+import biblemulticonverter.data.Utils;
 import biblemulticonverter.data.FormattedText.FormattingInstructionKind;
 import biblemulticonverter.format.paratext.ParatextCharacterContent.AutoClosingFormatting;
 import biblemulticonverter.format.paratext.ParatextCharacterContent.ParatextCharacterContentPart;
@@ -524,10 +525,13 @@ public static Set<ParagraphKind> allForVersion(Version version) {
 	}
 
 	public static class TableCellStart implements ParatextBookContentPart {
+
+		public static final String TABLE_CELL_TAG_REGEX = "t[hc](c|r?[0-9]+(-[0-9]+)?)?";
+
 		private final String tag;
 
 		public TableCellStart(String tag) {
-			this.tag = tag;
+			this.tag = Utils.validateString("tag", tag, TABLE_CELL_TAG_REGEX);
 		}
 
 		public String getTag() {

biblemulticonverter/src/main/java/biblemulticonverter/format/paratext/ParatextDump.java

@@ -155,7 +155,7 @@ protected void doExportBook(ParatextBook book, File outFile) throws IOException
 		}
 	}
 
-	private void writeBook(BufferedWriter bw, ParatextBook book) throws IOException {
+	protected void writeBook(BufferedWriter bw, ParatextBook book) throws IOException {
 		bw.write("BOOK\t" + book.getId().getIdentifier() + "\t" + book.getBibleName() + "\n");
 		for (Map.Entry<String, String> bookattr : book.getAttributes().entrySet()) {
 			bw.write("BOOKATTR\t" + bookattr.getKey() + "\t" + bookattr.getValue() + "\n");